mcpField
A
agent-magnet

agent-magnet

Local
github.com/helinakdoganMemory & Knowledge14Updated 8w ago
Repository

About agent-magnet

agent-magnet is a local-by-default memory layer for people using Claude, Cursor, and Codex. It automatically organizes project context and preferences across sessions, with options to remove or complete memories and share them with a team.

Key features

  1. 01Automatically captures work context
  2. 02Shared memory across Claude, Cursor, and Codex
  3. 03Organizes decisions, preferences, and goals
  4. 04Forget memories or mark them done
  5. 05Team memory sharing

Use cases

  1. 01Carry project context between AI sessions
  2. 02Reuse preferences and conventions across supported tools
  3. 03Share a team decision as context for others

MCP support

It provides an MCP server for Codex and other MCP clients. The `agent-magnet init` command detects and configures Claude Code, Claude Desktop, and Cursor.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "helinakdogan-agent-magnet": {
      "command": "uvx",
      "args": [
        "agent-magnet"
      ],
      "env": {
        "MAGNET_USER_ID": "<MAGNET_USER_ID>",
        "MAGNET_OPENAI_KEY": "<MAGNET_OPENAI_KEY>",
        "MAGNET_LOCAL_MODE": "<MAGNET_LOCAL_MODE>",
        "MAGNET_REDIS_URL": "<MAGNET_REDIS_URL>",
        "MAGNET_PROJECT_ID": "<MAGNET_PROJECT_ID>"
      }
    }
  }
}
Run commanduvx agent-magnet
Environment variables to set
MAGNET_USER_IDYour identifier used as the memory key across all tools
MAGNET_OPENAI_KEYSecretOpenAI API key for the reflector and classifier models
MAGNET_LOCAL_MODESet to 1 to use local SQLite storage — no Redis or external services needed
MAGNET_REDIS_URLRedis connection URL for persistent shared storage (overrides local mode)
MAGNET_PROJECT_IDNamespace for memory isolation across projects (defaults to 'default')

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiagent-magnet0.1.11

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Agent Magnet

PyPI README image

Your AI forgets your project every new session. This fixes that.

What it does

  • Learns automatically as you work — no "remember this" required
  • Shares one memory across Claude, Cursor, and Codex
  • Lets you forget or mark things done — memory doesn't just pile up

Quick start

pip install agent-magnet
agent-magnet init

That's the whole install. No Redis, no keys, local by default.

What it remembers

Decisions, conventions, watch-outs, failed attempts, goals, preferences, and actions taken — one memory, sorted automatically.

Team memory

Shared memory for a team — one person's decision becomes everyone's context. Requires a paid Agent Magnet key from agentmagnet.app.

Works everywhere

Claude, Cursor, Codex — same memory, local by default. agent-magnet init detects and configures Claude Code, Claude Desktop, and Cursor for you.

Manual MCP config (Codex, or any other MCP client) 
{
  "mcpServers": {
    "agent-magnet": {
      "command": "agent-magnet-mcp",
      "env": { "MAGNET_USER_ID": "your_name" }
    }
  }
}

MIT licensed. Contribute — and a ⭐ if this saved your context window.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.